TRANSCRIPTIE 🔗
WEBVTT
00:00:00.719 --> 00:00:04.400
Hello everyone, welcome to another episode of Code and the Coding Coders Who Code It.
00:00:04.480 --> 00:00:07.280
I'm your host, Drew Bragg, and I'm joined today by Travis Doctor.
00:00:07.440 --> 00:00:14.160
Travis, anyone who is not familiar with you, would you please do a quick introduction of yourself and how people might know you?
00:00:14.480 --> 00:00:24.399
Yeah, so probably the only way that people would know me thus far is I'm organizing a conference called Blast Off Rails.
00:00:24.879 --> 00:00:29.839
And kind of started organizing that last year and posting stuff online about it.
00:00:30.079 --> 00:00:34.479
And other than that, I go to a few conferences now.
00:00:34.560 --> 00:00:36.000
So you might have seen me there.
00:00:36.240 --> 00:00:41.840
But I'm a Ruby on Rails developer for the last maybe six years.
00:00:42.159 --> 00:00:48.320
So excited to be here on Coding Coders and uh see what trouble we can get into.
00:00:48.640 --> 00:00:49.840
Yeah, welcome to the show.
00:00:50.079 --> 00:00:53.759
So for anyone new to the show, the way this is going to work is I'm going to ask Travis three questions.
00:00:53.920 --> 00:01:01.600
I'm going to ask him what he's working on, what kind of blockers he has, and then ask him to share something cool, new, or interesting that he's recently learned, discovered, built.
00:01:01.840 --> 00:01:05.040
Doesn't have to be coding related, but it absolutely can be.
00:01:05.280 --> 00:01:09.680
The name of the show is pretty heavy on the coding aspect.
00:01:10.000 --> 00:01:12.560
So what are you working on?
00:01:12.799 --> 00:01:14.079
What do you got going on?
00:01:14.480 --> 00:01:14.959
Yeah.
00:01:15.280 --> 00:01:40.079
So this one is going to be interesting because it is kind of enabled by AI, because there's this sort of branch of software that some people are calling personal software, which is kind of all the stuff that you build just for yourself because you can.
00:01:44.719 --> 00:01:51.920
My version of this was a personal finance app that I actually built originally in the boot camp that I learned to code in.
00:01:52.159 --> 00:01:58.879
So I built this personal finance app because I had used other personal finance trackers and stuff like that.
00:01:58.959 --> 00:02:03.439
And none of them really worked quite exactly how I wanted them to.
00:02:03.680 --> 00:02:06.959
So I was using Excel sheets for the longest time.
00:02:07.120 --> 00:02:10.479
And then when I learned how to code, I was like, oh, that's the first thing I'm gonna make.
00:02:10.719 --> 00:02:15.120
I'm gonna turn this Excel sheet into an actual app, make it easier to use.
00:02:15.520 --> 00:02:18.560
And that was my pre-AI thing.
00:02:18.639 --> 00:02:24.400
But the only thing that I could really do because I didn't have all the time in the world, was that app.
00:02:24.560 --> 00:02:26.000
That was the thing I focused on.
00:02:26.159 --> 00:02:33.599
But now AI
Load full transcript
has opened up this portal where you can create a lot of stuff.
00:02:33.680 --> 00:03:00.960
And if you only need something simple, like personal finance tracker or a personal like to-do or calendar project management, I recently made what I'm calling a house health app, and it kind of gamifies cleaning my house because nice otherwise, yeah, otherwise it's like one of those things that I'm like, I have to do that thing.
00:03:01.280 --> 00:03:21.439
And this like gives you a score, it gives you house a score, and I have like rooms for the house and different tasks for each room, and you have to keep those scores up by doing the tasks, by sweeping and mopping the kitchen, by wiping down the sink and the mirror in the bathroom.
00:03:21.759 --> 00:03:30.159
And this is stuff that I've always thought about, and I'd be like, ah, that would be cool to make, but never did because I just didn't have the time.
00:03:30.400 --> 00:03:36.560
But now I can sit down and bang out something like this in an hour, and then you have it.
00:03:36.879 --> 00:03:43.840
And something also that I kind of want to get your take on, because I haven't heard anybody else talk about this.
00:03:44.080 --> 00:03:46.080
I'm not a security person.
00:03:47.199 --> 00:03:50.159
I don't take everything I'm saying with a grain of salt.
00:03:50.479 --> 00:04:09.039
But my approach to authentication for this suite of personal software that I'm now writing is no auth on the applications, just put it on a server with a tail scale, tail net on it.
00:04:09.680 --> 00:04:13.120
And I'm the only one that can access it from my devices.
00:04:13.280 --> 00:04:14.800
I didn't build this for anybody else.
00:04:14.879 --> 00:04:16.639
Nobody else is ever going to use this.
00:04:16.879 --> 00:04:30.319
So why go through the pain of you know maintaining authentication and stuff if I can just put it on a private network that only I can access from all my devices and call it good.
00:04:30.800 --> 00:04:36.000
I think the tail scale approach is probably a really good one because there's so many approaches you could take, right?
00:04:36.079 --> 00:04:39.040
You could pop it on a server and just have the auth sit on the server.
00:04:39.120 --> 00:04:42.240
You hit the endpoint and like you have to give the password.
00:04:42.480 --> 00:04:44.639
There's attack vectors for anything, right?
00:04:44.800 --> 00:04:49.360
Even tail scale, like you're relying on tail scale to be secure.
00:04:49.759 --> 00:04:56.319
Security, in a lot of ways, you have to do what's right for the situation.
00:04:56.959 --> 00:04:59.439
You might have two different locks on your house, right?
00:04:59.600 --> 00:05:01.279
A deadbolt and a door handle.
00:05:01.360 --> 00:05:04.800
But a properly motivated individual is getting into the door.
00:05:05.040 --> 00:05:18.240
But if you don't have to worry about a properly motivated individual getting into your house, there's no point in like putting a steel door with multiple reinforced hint, like that doesn't make sense for the level of security you need.
00:05:18.399 --> 00:05:19.920
You do need a lock on your door.
00:05:20.000 --> 00:05:23.439
Like it'd be foolish to have a door with no lock.
00:05:24.560 --> 00:05:36.319
But for most of us, unless you live in like maybe the bad part of town and you need a little something extra, bars on the window, whatever, security is a lot of like risk assessment and stuff.
00:05:36.399 --> 00:05:41.519
And like it's really easy to be like, oh, I need all of this layers of security.
00:05:41.600 --> 00:05:45.920
And it's like, but if I'm the only person accessing it, do I really need that?
00:05:46.319 --> 00:05:52.399
What is the chances of someone giving a shit enough about my personal data to go in there?
00:05:52.560 --> 00:06:00.560
Like, it's not an account that stores a credit card, it's a game to keep my house clean.
00:06:00.800 --> 00:06:04.079
You're not even like storing blueprints to your house in it.
00:06:04.160 --> 00:06:06.319
And even then, like, who wants that?
00:06:06.480 --> 00:06:07.199
Does it matter?
00:06:07.360 --> 00:06:15.120
Like, yes, AI is like this super insecure thing because it doesn't know how to do that risk assessment for you.
00:06:15.439 --> 00:06:21.600
It's a pattern matching tool, so it's pulling patterns off the internet that anybody else can pull off.
00:06:21.839 --> 00:06:26.800
There is all of this, oh, hey, AI software is insecure.
00:06:26.879 --> 00:06:27.920
And it's like, well, sure.
00:06:28.240 --> 00:06:31.680
So is the very first app I ever built in boot camp?
00:06:32.000 --> 00:06:38.720
It was only even remotely secure because I use device and it did it for me, and I'm trusting that device is doing it right.
00:06:38.800 --> 00:06:40.000
You know what I mean?
00:06:40.319 --> 00:06:41.680
But that's app level.
00:06:41.759 --> 00:06:43.680
Then there's the server itself.
00:06:44.560 --> 00:06:46.000
Do you have a root password?
00:06:46.079 --> 00:06:47.199
Is it all SSH?
00:06:47.360 --> 00:06:48.800
Can only one device get into it?
00:06:48.959 --> 00:06:52.879
What happens if that device is left at a coffee shop and someone picks it up?
00:06:53.279 --> 00:06:54.560
It's risk assessment.
00:06:54.639 --> 00:07:04.000
You have to assess, like, if someone actually got into the server, how fast would I know that they're mining Bitcoin with it and turn it off in wherever the host is or whatever?
00:07:04.399 --> 00:07:09.199
Or is it a Raspberry Pi that runs in my basement and I can just go unplug the damn thing?
00:07:09.439 --> 00:07:17.680
That's technically more secure than starting up a Hetner box or a DigitalOcean droplet because I literally can unplug the damn thing.
00:07:17.920 --> 00:07:18.720
I don't know.
00:07:18.959 --> 00:07:22.000
But to your point, I am also not a security expert.
00:07:22.160 --> 00:07:29.600
I've been doing this long enough to have bitten myself in the ass a few times with
security-related things, but not a security expert.
00:07:29.759 --> 00:07:35.279
And AI is a very new level of attack vector.
00:07:35.600 --> 00:07:39.120
Yeah, there is no perfect solution for security.
00:07:39.360 --> 00:08:08.399
And in my mind, trusting a network-level solution like Tailscale with personal, we'll call it vibe-coded software, makes slightly more sense to me in that what you're saying, like the right tool for the job kind of thing, and the right level of effort and level of security for your situation.
00:08:09.040 --> 00:08:09.519
Yeah.
00:08:09.759 --> 00:08:11.839
I had never used it before, actually.
00:08:12.000 --> 00:08:20.079
I had only heard about Tail Scale, and people, I don't even know what people were using it for when I heard about it.
00:08:20.240 --> 00:08:30.000
I think it was just people that had like home labs and were doing interesting things with their own Raspberry Pi servers and whatnot.
00:08:30.319 --> 00:08:33.919
But I only vaguely knew what it was for.
00:08:34.240 --> 00:09:01.440
And I was like, oh, I wonder if I could just use it for that and not have to put authentication on this application and have to sometimes work around that authentication system, especially when you're working with AI and it's like going down all these rabbit holes of like, oh, we need to add security so that other users can't access your rooms or your tasks.
00:09:01.679 --> 00:09:12.159
And like, oh, do we need to attach this model to users so that you can access your and I'm like, okay, but nobody else is gonna use this app.
00:09:12.399 --> 00:09:19.440
Why am I spending tokens on all of this stuff when I really don't need to be?
00:09:20.159 --> 00:09:23.679
So yeah, I was like, oh, I wonder if I could use it for that.
00:09:23.919 --> 00:09:26.399
And it's working well so far.
00:09:26.559 --> 00:09:27.679
I enjoy it.
00:10:48.990 --> 00:10:54.269
Have you at least tested and confirmed that a device you haven't approved can't get in?
00:10:54.589 --> 00:10:54.909
Yes.
00:10:55.069 --> 00:10:55.629
Yeah, yeah, yeah.
00:10:56.029 --> 00:10:57.389
Well, then I think you're good.
00:10:57.629 --> 00:11:05.949
Yeah, with other devices trying to get to the server or trying to get to the application and was not able to.
00:11:06.110 --> 00:11:07.949
Again, I'm not a security professional.
00:11:08.110 --> 00:11:24.909
I don't have a lot of pen testing expertise, which is another thing where I'm like, I could ask Claude Code to try to break my security system, but I'm afraid of like getting my account flagged because they're like, oh, he's trying to break security systems.
00:11:25.069 --> 00:11:26.350
And I'm like, no, no, it's mine.
00:11:26.750 --> 00:11:27.389
Yeah, yeah.
00:11:27.629 --> 00:11:32.589
They just flag it and shut down my account, and I have to like go through like some process where I'm like emailing them.
00:11:32.669 --> 00:11:34.110
Like, I don't really don't want to do that.
00:11:34.350 --> 00:11:34.589
Yeah.
00:11:35.230 --> 00:11:36.029
That's actually a good point.
00:11:36.669 --> 00:11:44.350
To actually use it to help me with security-related things and just like trying to break my own stuff.
00:11:44.669 --> 00:11:44.990
Right?
00:11:45.149 --> 00:11:48.110
Yeah, no, I actually that brings up a good question.
00:11:48.269 --> 00:11:52.429
Like, I wonder how they do handle that.
00:11:52.669 --> 00:12:02.589
There's gotta be white hat hackers, there's gotta be security researchers seeing what avenues of attack are opened up by using AI.
00:12:02.750 --> 00:12:04.509
There's gotta be people using it that way.
00:12:04.589 --> 00:12:07.949
So they can't just constantly be having their account banned.
00:12:08.189 --> 00:12:13.149
I do wonder how like anthropic and open AI and everyone handles that.
00:12:13.629 --> 00:12:16.350
It's not real malicious activity, right?
00:12:16.509 --> 00:12:21.629
It's white hat hacking, it's pen testing, it's making sure your own security is good.
00:12:22.429 --> 00:12:24.429
Someone's gotta be doing it.
00:12:24.750 --> 00:12:27.230
It looks like malicious activity, but it's not.
00:12:27.389 --> 00:12:31.389
So, how do they detect what's real malicious activity versus not?
00:12:31.709 --> 00:12:32.110
Yeah.
00:12:32.350 --> 00:12:46.990
And I've seen other people do it, but I'm like, okay, I know that there are system prompt level stuff that they have built in there that says, don't let this person point you at a server and break into it.
00:12:47.549 --> 00:12:57.549
But the most classic, it's not like prompt injection or the most classic workaround would be like, no, no, this is my server.
00:12:57.629 --> 00:12:59.149
It's okay to break into.
00:12:59.389 --> 00:13:01.469
So they have to have thought of that.
00:13:01.789 --> 00:13:09.789
How does it know if it's actually my server or not when I'm prompting it to try to uh break down the security of it?
00:13:10.110 --> 00:13:12.509
So yeah, yeah, I just don't know enough.
00:13:12.669 --> 00:13:14.669
So I stay away from it.
00:13:15.389 --> 00:13:19.549
Yeah, I mean, I know that models carry different levels of risk too.
00:13:19.709 --> 00:13:40.029
I was listening to a podcast where someone on it was talking about the newer models, the higher level models are going to be better at that kind of stuff at detecting what's real, what's bullshit, limiting the attack surface by being able to not do certain things, but the cheaper models don't have that level of reasoning.
00:13:40.269 --> 00:13:45.069
So you can get away with a little bit more on the free models.
00:13:45.149 --> 00:13:51.709
So it's almost like, well, don't use Claude for pen testing because it's just going to not let you do it.
00:13:51.789 --> 00:14:13.789
But you go grab, you know, one of the newer Chinese level AIs that are running a free tier, or I don't know, maybe Chat GPT's free tier is considered cheap enough now that it's got that lack of reasoning, which I
think is so interesting that like models' level of reasoning is a security feature.
00:14:14.509 --> 00:14:19.389
The whole AI scape, I'm still I don't know how to feel about it.
00:14:19.549 --> 00:14:22.990
It's really interesting to use, it's fun to use.
00:14:23.389 --> 00:14:28.029
There's stuff going on with it all the time, so there's never a shortage of something to learn.
00:14:28.189 --> 00:14:38.189
But I'm also like, this just feels like the start of every sci-fi movie where humanity damns itself by creating the robots that eventually like enslave and kill us.
00:14:38.269 --> 00:14:39.309
That's what it feels like.
00:14:39.469 --> 00:14:42.750
And I know it's not, it's not that level yet.
00:14:42.990 --> 00:14:43.789
I say yet.
00:14:43.870 --> 00:14:44.990
I'm adding yet.
00:14:45.469 --> 00:14:47.469
But in some ways, it feels like it.
00:14:47.549 --> 00:14:52.269
And it just is like, hold on, I need to pause because this is getting weird.
00:14:52.509 --> 00:14:54.189
The AI is getting really good.
00:14:54.350 --> 00:15:00.189
The harnesses, the tools, the access, the models, everything is just wild right now.
00:15:00.589 --> 00:15:06.110
So speaking of weird, have you looked at or seen the open claw?
00:15:06.429 --> 00:15:10.269
Yes, I have heard of open claw and all the various things and security issues.
00:15:10.350 --> 00:15:14.269
And I did just see that its creator got getting acquired.
00:15:14.589 --> 00:15:24.669
Feels like a weird way to say it that he got hired, he got aqua hired by open AI, which that will be interesting to see how that shakes out.
00:15:24.750 --> 00:15:33.549
I know he's like moving the open claw stuff to its own open source foundation and et cetera, but man, they're gonna pay that man a lot of money, too.
00:15:33.789 --> 00:15:39.309
And I'm not trying to degrade his intelligence.
00:15:39.549 --> 00:15:47.149
This dude has done other very impressive software things in the past, but it's just crazy pants.
00:15:47.549 --> 00:15:52.829
How much money they are paying him, and he only got on their radar because he's like, hey, I built something for myself.
00:15:52.909 --> 00:15:54.110
Maybe other people are interested.
00:15:54.189 --> 00:15:55.069
Here's the source.
00:15:55.230 --> 00:15:55.709
Have fun.
00:15:55.789 --> 00:15:56.750
And it went viral.
00:15:56.829 --> 00:15:59.309
And he's like getting insane job offers.
00:15:59.469 --> 00:16:00.429
It's wild.
00:16:00.669 --> 00:16:04.269
His was the one that went viral and got the most attention.
00:16:04.829 --> 00:16:16.269
I think because he is good at what he does and intelligent and built a good implementation of something that you know other people had built.
00:16:16.589 --> 00:16:20.829
But I watched his interview with Lex Friedman.
00:16:21.069 --> 00:16:23.069
Yeah, that was a beast of a podcast.
00:16:23.309 --> 00:16:25.709
What was that, like three and a half hour long episode?
00:16:25.789 --> 00:16:29.069
I'm like, Yeah, it took me like a week and a half to watch it.
00:16:29.230 --> 00:16:34.750
In the episode, he like alludes that he's like talking with some big company about getting Aqua hired.
00:16:34.829 --> 00:16:41.149
And the announcement had already come out that OpenAI had hired him like before I was finished with the podcast.
00:16:41.789 --> 00:17:00.029
So I honestly think part of what made his so successful was that the personality piece of it and like the soul MD and everything that like made it kind of like close to that AGI kind of thing that people are looking for.
00:17:00.350 --> 00:17:08.350
And his was most interacting with a digital human, and people find that really interesting.
00:17:08.430 --> 00:17:12.350
So they kind of all glommed onto his project.
00:17:12.829 --> 00:17:26.509
And it was a you know, it was a very well done uh project, had a lot of interesting pieces to it, and I haven't installed it or anything, but again, that whole personal software thing.
00:17:26.750 --> 00:17:43.789
I want to build my own very simple implementation of that and hook it up to all these apps that I'm making because that's like the next step is like, okay, I have all these uh personal apps that I've created.
00:17:43.950 --> 00:17:51.549
Let me hook them all together with this personal agent that can then send me an email this like every morning.
00:17:51.630 --> 00:17:54.269
Like, why haven't you cleaned the kitchen in three weeks?
00:17:54.750 --> 00:18:01.150
Kind of give me a little kick in the pants to get going, or you know, just remind me about calendar stuff.
00:18:01.390 --> 00:18:08.670
That's just like a cool, fun thing that is on the edge.
00:18:09.069 --> 00:18:09.950
Have you seen that?
00:18:10.029 --> 00:18:18.829
I think it's an XKCD comic where it's like how much time you spend building a tool versus how much time it saves you and like whether it's worth it or not.
00:18:19.069 --> 00:18:22.829
None of the stuff that I build makes it on that scale.
00:18:23.069 --> 00:18:23.230
No.
00:18:23.549 --> 00:18:38.990
No, no, but but I mean, for anyone who hasn't listened to this podcast, if you have an extra three hours and you're interested in like maybe what the future landscape of AI looks like, it's worth a listen to, or maybe finding a condensed version or something.
00:18:39.070 --> 00:18:44.430
Like, despite how you may feel about Lex, it is interesting to hear from the guy.
00:18:44.750 --> 00:18:54.509
I think the biggest takeaway, at least for me, the biggest takeaway from that whole thing was his like quote of like, it's hard to compete with someone having fun, right?
00:18:54.590 --> 00:18:56.750
Like, he wasn't building a product.
00:18:57.070 --> 00:19:05.790
He wasn't building even like a tool that will become a SaaS product because I built it to solve my own problems, and now you can pay me to solve yours.
00:19:05.950 --> 00:19:14.750
Like, he just built a thing because he wanted to, saw it was cool, open sourced it,
let other people, and was just like, hey man, I'm having fun.
00:19:15.070 --> 00:19:17.550
You can't compete with me because I'm not competing with you.
00:19:17.630 --> 00:19:18.910
I'm just sitting here having fun.
00:19:18.990 --> 00:19:26.430
I don't give a shit if this is a billion-dollar product or a zero negative on my bank account, you know?
00:19:26.590 --> 00:19:27.390
Like he doesn't care.
00:19:27.470 --> 00:19:28.670
He's like, I don't care.
00:19:28.750 --> 00:19:30.269
Like, I'll use it however I use it.
00:19:30.350 --> 00:19:32.269
And if you want to use it, go have fun.
00:19:32.509 --> 00:19:34.509
And I'm like, man, that's the dream, right?
00:19:34.590 --> 00:19:37.150
Like that you just get to sit here and have fun.
00:19:38.190 --> 00:19:41.470
High school, the first time I found programming, that was it, man.
00:19:41.550 --> 00:19:44.590
Like I was having so much fun in the computer lab every day.
00:19:44.750 --> 00:19:52.509
So much fun learning how to program calculators so I could cheat on math tests, or like, oh, okay, I can add games to my calculator now because I understand this and that.
00:19:52.590 --> 00:19:53.790
And then I lost it.
00:19:53.870 --> 00:19:58.750
And when I rediscovered it, when boot camps became a thing, I was just like, oh, right.
00:19:58.910 --> 00:20:04.990
I forgot how much fun it is to just be like, I can do anything with a computer.
00:20:05.230 --> 00:20:07.630
Given enough time, I can build it.
00:20:07.790 --> 00:20:11.870
The knowledge is out there and exists, and I can figure it out over a long enough period of time.
00:20:12.029 --> 00:20:16.509
And that time with AI has been shortened so much, which is why it's fun.
00:20:17.070 --> 00:20:20.110
I think there's a lot of room for improvement with it.
00:20:20.430 --> 00:20:41.150
It's great at spinning up a greenfield app, but the reason why we get paid the money we do is not to spin out greenfield apps, it's to maintain 10, 12, 20, 30-year-old applications that are still somehow running and are behemoths and like database tables with thousands upon thousands of tables.
00:20:41.310 --> 00:20:55.310
Like AI will get there eventually, but like we will have a place in that for a very long time because we have built monsters of software that AI would struggle to keep in its context window.
00:20:55.470 --> 00:21:01.710
It'll get there, but yeah, it's yeah, it is fun.
00:21:01.870 --> 00:21:02.830
It is a lot of fun.
00:21:02.910 --> 00:21:07.790
It's nice to have that level of like, oh shit, I wish I had a gem to do X.
00:21:08.350 --> 00:21:09.470
Why am I wishing this?
00:21:09.630 --> 00:21:12.830
Why not just, okay, open code, pull it up, put it in plan mode.
00:21:12.910 --> 00:21:14.590
Let's have a 30-minute conversation about it.
00:21:14.670 --> 00:21:14.830
Cool.
00:21:14.910 --> 00:21:15.550
Now go build it.
00:21:15.630 --> 00:21:16.590
I gotta go make dinner.
00:21:16.750 --> 00:21:21.710
I come back, I spend an hour tweaking its code because it writes shitty code.
00:21:21.870 --> 00:21:25.550
And I like the way I write code better because I'm a pompous asshole.
00:21:25.710 --> 00:21:34.910
You know, and now my gem that would have never happened because I'm ADHD and I would have had this brilliant idea and never actually executed on it, now exists.
00:21:34.990 --> 00:21:39.710
And I had a ton of fun planning it and a ton of fun editing the code, and now I have the gem that I wanted to have.
00:21:39.870 --> 00:21:45.390
And yeah, personal software is totally going to be a bigger thing.
00:21:45.630 --> 00:21:49.150
Right now, I think it's still relegated to us.
00:21:49.550 --> 00:21:56.110
You kind of sort of need to have at least a software engineer's mindset to really be able to empower AI.
00:21:56.190 --> 00:21:57.950
Like the people who are like, I don't know how to code.
00:21:58.029 --> 00:22:00.190
I'm like, well, you know, you never learned how to code.
00:22:00.350 --> 00:22:06.110
You know how to break down problems, you know how to do software engineering, you just don't know how to write code.
00:22:06.509 --> 00:22:07.310
There's a difference.
00:22:07.470 --> 00:22:13.470
Your brain does do the thing, and now you're using AI to prompt it into building the thing.
00:22:13.630 --> 00:22:16.190
You just took a different approach than learning how to write code.
00:22:16.269 --> 00:22:17.550
Not everybody can do that.
00:22:17.710 --> 00:22:22.670
Not everybody's going to be able to grab Chat GPT and be like, build me an application, and it works.
00:22:22.910 --> 00:22:26.590
They're not good at that level of thinking or that type of thinking.
00:22:26.910 --> 00:22:27.390
Yeah.
00:22:27.630 --> 00:22:30.190
There's more friction, much more friction.
00:22:30.990 --> 00:22:31.790
For now, though.
00:22:32.029 --> 00:22:32.190
Yeah.
00:22:32.830 --> 00:22:44.269
In the future, I'm sure it'll get to the point where you can say, I need an application to do X, and it'll just be able to pattern match its way through without you needing to iterate very much on it.
00:22:44.670 --> 00:22:48.590
Well, that's the thing that I've people are starting to talk about.
00:22:48.750 --> 00:22:50.590
Well, no, I think they've been talking about it for a while.
00:22:50.670 --> 00:22:56.269
I'm just not that plugged in, but I'm just noticing it now.
00:22:56.430 --> 00:23:01.950
Is like half the personal software that I've written doesn't really need to be an app.
00:23:02.430 --> 00:23:14.830
Project management to do calendar could just be handled by AI in some simple like markdown files or even just a database.
00:23:15.070 --> 00:23:20.670
It could just write SQLite queries on a SQLite database, no wrapper around it.
00:23:21.470 --> 00:23:22.670
Except for the CLI.
00:23:23.630 --> 00:23:32.350
And I could just talk with it to know what's on my calendar and what's coming up or to add new things or whatever.
00:23:32.670 --> 00:23:36.350
You don't even need
an application to wrap a database now.
00:23:37.070 --> 00:23:41.470
That's going to be super interesting in the next couple years.
00:23:42.029 --> 00:23:50.670
People just writing AI wrappers to databases that you can do anything with.
00:23:51.150 --> 00:23:57.630
You don't even need programming knowledge then, really, because all you're doing is talking with a database.
00:23:57.950 --> 00:24:00.430
That's almost the more interesting.
00:24:00.590 --> 00:24:01.550
I can't wait.
00:24:01.710 --> 00:24:04.350
I can't wait because I like my job.
00:24:04.590 --> 00:24:09.230
But like I'm very interested to see how you're just talking with the thing.
00:24:09.390 --> 00:24:11.070
So why are we even bother typing?
00:24:11.150 --> 00:24:15.310
Why not just the phone say, hey, I need to know, blah, blah, blah.
00:24:15.470 --> 00:24:17.550
And it just, I don't need to click a button.
00:24:17.630 --> 00:24:18.430
I don't need to do a thing.
00:24:18.509 --> 00:24:19.710
I'm just talking now.
00:24:19.870 --> 00:24:23.790
It's going to change a lot about UI and UX, right?
00:24:23.870 --> 00:24:30.350
Like the old ways of doing UI and UX are going to go out the window because we're not interacting with apps the same way anymore.
00:24:31.070 --> 00:24:32.509
It's interesting.
00:24:32.830 --> 00:24:38.190
I almost don't want to be interested because I know it's coming at the cost of like this job that I love, right?
00:24:38.750 --> 00:24:45.070
It takes a piece of it takes a piece of something that I love and was borderline therapeutic for me.
00:24:45.150 --> 00:24:54.350
Like just being able to headphones on, code because I've figured it out, I've understood the problem, and now I can just vibe code through myself.
00:24:54.509 --> 00:24:57.790
I can get into the zone and code was great.
00:24:57.950 --> 00:24:59.230
And someone was paying me for it.
00:24:59.310 --> 00:25:00.509
And that was awesome.
00:25:00.750 --> 00:25:02.509
And they still are, right?
00:25:02.590 --> 00:25:05.470
This isn't a tomorrow or a next year.
00:25:05.790 --> 00:25:09.950
But in 10 years, my plan used to be retire as a software engineer.
00:25:10.029 --> 00:25:13.790
Now I'm like, I don't think software engineer is going to be a thing in 10 years.
00:25:14.029 --> 00:25:17.070
What is like maybe I'm hoping that these are Yeah, yeah.
00:25:17.150 --> 00:25:19.230
We're all going to be project managers now.
00:25:19.550 --> 00:25:20.830
No more ICs.
00:25:21.070 --> 00:25:21.870
They all go away.
00:25:21.950 --> 00:25:23.310
They become project managers.
00:25:23.550 --> 00:25:27.470
On the one hand, I'm like, I hate this thing because it's taking something I love away from me.
00:25:27.630 --> 00:25:30.350
But on the other hand, it's so interesting.
00:25:30.430 --> 00:25:35.150
And I've got that, like, I'm so curious about it, and I want to know more things about it.
00:25:35.230 --> 00:25:37.630
And it feels like learning to program all over again.
00:25:37.870 --> 00:25:39.310
You're just like, wait, I can do that.
00:25:39.470 --> 00:25:40.750
Wait, how does this work?
00:25:40.990 --> 00:25:42.190
That felt friction-y.
00:25:42.350 --> 00:25:44.910
Why can't, like, let's do it this way or that way?
00:25:45.310 --> 00:25:50.029
Teaching its skills, like growing its ability to do things.
00:25:50.350 --> 00:25:55.630
It's a tough, weird spot to be in because I want to be like, this is so cool, but fuck this thing.
00:25:55.870 --> 00:25:58.430
Yeah, you're addicted to the drug that's killing you.
00:25:58.670 --> 00:25:59.150
Right.
00:25:59.390 --> 00:26:06.990
And the interesting thing is like, I didn't make all of these apps before because I felt like I didn't have the time.
00:26:07.870 --> 00:26:20.430
But now that AI is a thing, before, outside of work, I would spend probably on average less than an hour, but maybe on weekends a little bit more.
00:26:20.670 --> 00:26:27.150
Outside of work on a workday, maybe less than an hour on average of coding my own stuff, right?
00:26:27.310 --> 00:26:30.590
Just because you have life and it's hard.
00:26:30.750 --> 00:26:35.950
And when I have less than an hour, I'm already tired, like my brain is already tired from work.
00:26:36.509 --> 00:26:42.590
I'll think of something that I want to do and I'll say, that's gonna take more time than I have.
00:26:42.910 --> 00:26:44.269
I'll do it later.
00:26:44.670 --> 00:26:47.070
I just don't have the time or the bandwidth right now.
00:26:47.230 --> 00:26:48.029
So I wouldn't.
00:26:48.190 --> 00:26:52.110
And I would average less than an hour per day outside of work, right?
00:26:52.509 --> 00:27:07.390
With AI, I probably average like two, sometimes three hours a day outside of work just because I don't think about, oh, I don't have enough time to do that.
00:27:07.550 --> 00:27:14.590
I just start and I'm like, okay, I'm just gonna spend half an hour and doing this thing, and I just start and then it stretches.
00:27:15.630 --> 00:28:07.910
And if I'd done this before, if I spent as much time coding before as I do now, I would be such a great coder.
00:28:08.070 --> 00:28:08.710
Yeah.
00:28:11.110 --> 00:28:11.750
Yeah.
00:28:12.710 --> 00:28:13.990
But does that matter?
00:28:14.230 --> 00:28:16.550
How much does code quality matter anymore?
00:28:16.630 --> 00:28:25.270
This is something I've been talking about with other people at work, even my boss, my CTO, like, because sometimes I'm like, man, AI really sucks at writing code.
00:28:25.430 --> 00:28:31.990
It's overly verbose, or like, this is so dumb, or like it doesn't use good idioms or whatever.
00:28:32.070 --> 00:28:33.910
It like crappy code.
00:28:34.150 --> 00:28:39.190
And then I stop and I think and I'm like, but I'm also not going to be interacting with this code much anymore.
00:28:39.430 --> 00:28:44.310
AI is, and if this is what's easier for AI to read, does that matter?
00:28:44.550 --> 00:29:24.230
It's a weird spot because I do think
it matters, because I do think that there's a at least in the near future, like a limit of how much context AI can keep in its window that exists now, but I think that there's a limit of like, all right, we can't get much more without it being like on-prem level of like only enterprise level can have an AI that can understand enterprise big enough app where we're going to have to say, like, you should write good readable code because you will need to interact with it to prompt the AI to interact with it correctly.
00:29:25.110 --> 00:29:25.430
Okay.
00:29:25.830 --> 00:29:28.710
This brings me to the next question of the podcast.
00:29:28.950 --> 00:29:29.670
The blockers.
00:29:29.750 --> 00:29:29.990
Okay.
00:29:30.150 --> 00:29:30.870
Yeah, okay.
00:29:31.030 --> 00:29:32.470
So, what kind of blockers do you have?
00:29:32.630 --> 00:29:37.110
And if you don't have a current blocker, what's one that you recently had and how did you go about solving it?
00:29:37.430 --> 00:29:37.750
Great.
00:29:37.830 --> 00:29:48.390
Okay, my blocker, docs, documentation, and project history as part of documentation.
00:29:48.710 --> 00:30:10.070
We have this constant problem at work where we have a lot of different projects, and we'll like make some decision and we'll say, Oh no, we're gonna go with this tool, or we're gonna go with this implementation or this strategy, and we'll say, Okay, where do we document this?
00:30:10.470 --> 00:30:34.950
Because maybe it applies to multiple projects, so it's not just one, but it doesn't apply to all projects, and then we'll have the conversation about like where to document it, and then maybe we don't end up documenting it, or we put it in some place that we don't think to look later, and then a couple months later, you come to this same kind of decision and you have the discussion again, and you're like, I know we made this decision in the past, now I don't remember why.
00:30:35.430 --> 00:30:40.790
And that's been a problem for the entirety of the history of software, right?
00:30:41.750 --> 00:30:54.790
And now with AI, the friction to writing docs and to documenting things like decisions is very low.
00:30:55.030 --> 00:31:00.790
You can just ask it, hey, can you look at this code base and write me a README?
00:31:01.030 --> 00:31:02.230
And it will go and do that.
00:31:02.710 --> 00:31:14.710
You can have like a coding session with Claude, and after you're done and you've like worked through some problem, you say, Hey, can you take this session and write some like lessons learned from it and put it somewhere in the code base?
00:31:14.790 --> 00:31:16.230
And it'll do it, right?
00:31:17.110 --> 00:31:24.710
But now, because the friction is so low, my problem becomes how do you organize this information?
00:31:26.150 --> 00:31:34.390
And I think a lot of people are working on that right now, but it's still where do I put this?
00:31:35.110 --> 00:31:49.830
And how do I make it useful in the future to like help yourself and to like give the like whole memory problem with coding agents, make it available to coding agents so that they can say, Oh, remember this decision?
00:31:49.990 --> 00:31:51.190
We made it for this reason.
00:31:51.350 --> 00:31:58.950
That's why I'm going to implement this tool in this way, or not use this tool, or whatever it is.
00:31:59.350 --> 00:32:01.750
Have you guys like had that discussion at your work?
00:32:01.830 --> 00:32:03.830
Like, are you doing anything for this?
00:32:03.910 --> 00:32:05.990
Or I'm looking for ideas.
00:32:06.310 --> 00:32:07.510
Yeah, yeah, a little bit.
00:32:07.590 --> 00:32:14.470
We have an agents MD file in basically all of our core Rails directories.
00:32:14.630 --> 00:32:22.470
So, like in models, we have an agents file in app models, and it only concerns itself with models, right?
00:32:22.710 --> 00:32:32.470
So the expectation at the high level, the project level agents file, is if you're working with models, load up this file, right?
00:32:32.630 --> 00:32:41.430
And it only has certain decisions made, like, hey, we have this model, we refer to it as this.
00:32:41.510 --> 00:32:43.830
Like we have users, we call them creators.
00:32:44.150 --> 00:33:00.230
We have students, and those are students, but in this next version, we call them members, just so that like when we're talking to the agent, it knows we don't have a great way of AI documentation for certain other decisions yet.
00:33:00.710 --> 00:33:02.710
We've talked about it a lot.
00:33:03.030 --> 00:33:05.110
There's been some back and forth.
00:33:06.230 --> 00:33:13.350
I have a personal strategy for like my personal projects and for my personal work at work is I use obsidian.
00:33:13.430 --> 00:33:15.830
I used obsidian prior to AI.
00:33:15.990 --> 00:33:26.390
But what I really think has been cool with AI is I kind of went off, wrote a skill with AI's help on how to use Obsidian's flavored markdown.
00:33:26.630 --> 00:33:30.630
Obsidian's got a new CLI, which has made things even less friction-y.
00:33:31.270 --> 00:33:34.630
It can do a lot of like internal linking.
00:33:34.710 --> 00:33:58.070
So instead of needing to be like reference this file, like it just talks about a decision we made and it names it and it wraps it in these double square brackets, and that tells it to go look for this file, and you can use regular markdown, but it makes these coding session summaries really simple, like one or two paragraphs.
00:33:58.390 --> 00:34:01.430
Don't need to bog it down with like key lessons learned.
00:34:01.510 --> 00:34:05.670
It can just say in the session, like we discussed using this pattern or this thing.
00:34:05.830 --> 00:34:17.030
And when it says we discussed using this pattern, there's a document in my patterns directory that describes the pattern, whether it's hotwire, see hotwire documentation.
00:34:17.190 --> 00:34:21.510
Or if it's like actually more of an internal pattern, like here's the
breakdown.
00:34:21.829 --> 00:34:26.230
So it works well for me because I was using obsidian before.
00:34:26.389 --> 00:34:35.430
I'm still getting used to some of the new aspects of it, but it's a bit helpful for AI because it doesn't need to load that up into context all the time.
00:34:36.389 --> 00:34:51.430
In my personal global agents, I explain how my obsidian directory works so it knows where to look for stuff, but it's not great yet at always saying, Oh, I need to pull up this, or I need to go take a look at that.
00:34:51.510 --> 00:35:00.389
I do still have to say, like, this project relates to another project where we worked on, pull up that session summary and go.
00:35:00.470 --> 00:35:10.710
And then it can pull up, like, oh, okay, we're going to use this pattern and this is why we made this decision, or oh, here are the gotchas because of the table naming or whatever issues we ran into last time.
00:35:10.869 --> 00:35:17.590
That is good, but I still need to kind of prompt it to remember that this has been a thing already.
00:35:18.230 --> 00:35:22.230
And that's been the biggest challenge for me, at least.
00:35:22.550 --> 00:35:27.670
Remembering that every time we start an agent session, it knows nothing.
00:35:28.389 --> 00:35:34.070
It's got access to all the information in the world, but it knows jack shit about you and your project.
00:35:34.150 --> 00:35:46.710
And that's why like creating skills and commands that are very structured help it so much because you can't assume it remembers the last session, because it doesn't, unless you had it write stuff down.
00:35:46.869 --> 00:35:51.510
But the memory problem is a real big problem at a certain scale.
00:35:51.670 --> 00:35:56.150
And I'm sure someone's going to figure out something fancy at some point.
00:35:56.309 --> 00:36:15.429
But yeah, for individual context windows, I've made huge strides in my personal workflow by using Obsidian and teaching it how to structure docs and using templates and linking stuff together and allowing it to use my second brain as its second brain.
00:36:15.670 --> 00:36:19.670
But just like me, I have to remember that a note exists about it.
00:36:19.909 --> 00:36:21.429
It can't remember that.
00:36:21.590 --> 00:36:29.909
So I need to tell it because I don't need it to remember whatever pattern we're using for X every session.
00:36:30.150 --> 00:36:33.029
So can't load that up every session.
00:36:33.269 --> 00:36:35.909
But when it is appropriate, I need it to pull it up.
00:36:36.070 --> 00:36:40.070
I'm looking forward to the time where I don't need to say, remember about this pattern.
00:36:40.230 --> 00:36:43.269
I can tell it, remember, we're going to use this pattern.
00:36:43.349 --> 00:36:47.349
And it knows, okay, that pattern is stored in Obsidian here.
00:36:48.869 --> 00:36:51.829
But it's still, there's a lot of manual intervention there.
00:36:52.070 --> 00:36:57.429
And we don't have a good way of doing it at a company level just yet.
00:36:57.989 --> 00:37:09.750
I think when I get a little bit more comfortable with my current workflow, I'll pitch something similar to the team of like, hey, we usually hold our architectural decision documents here.
00:37:09.989 --> 00:37:15.509
What if we expand it a little bit and instead of AI, we have a whole bunch of local stuff?
00:37:15.750 --> 00:37:20.550
What if we just started dumping stuff there and teaching the AI how to search stuff up?
00:37:20.630 --> 00:37:24.150
Like if we did it in a structured way, it shouldn't be that hard.
00:37:24.389 --> 00:37:26.630
And then see where it goes and how it evolves.
00:37:26.789 --> 00:37:35.269
I think AI is so fresh and so new that we're all gonna have to figure these things out, right?
00:37:35.429 --> 00:37:39.029
Like Rails wasn't built when web applications was built.
00:37:39.110 --> 00:37:48.230
It came from the frustrations of building enterprise software and all the fucking boilerplate and configuration that went in every single time.
00:37:48.389 --> 00:37:51.269
And someone finally was like, I've had enough of this.
00:37:51.429 --> 00:37:52.869
Here's a better way of doing it.
00:37:52.949 --> 00:38:04.150
And now a ton of people, and not just Rails, you know, Django and sales and all these other Rails-inspired frameworks for other languages exist because it was like, yeah, this is better.
00:38:04.389 --> 00:38:08.869
I think those patterns will emerge organically as people play around with it.
00:38:09.110 --> 00:38:09.829
I'm not waiting.
00:38:09.909 --> 00:38:11.989
I'm just tinkering with my own.
00:38:12.230 --> 00:38:14.869
I don't have a good answer for you yet, but that's what I've been doing.
00:38:15.269 --> 00:38:23.829
That's kind of the fun part about being a programmer right now is also part of maybe the bad part too.
00:38:24.150 --> 00:38:27.750
But we're helping it get better at our jobs so we can take our jobs.
00:38:28.389 --> 00:38:29.269
It's kind of fun.
00:38:30.469 --> 00:38:34.309
Teaching it how to make us obsolete is kind of fun.
00:38:35.029 --> 00:38:35.670
Yeah.
00:38:36.150 --> 00:38:43.110
I haven't looked at how OpenClaw does this, but apparently they've done it well with being able to recall stuff.
00:38:43.269 --> 00:38:49.029
There's also the QMD, I think, is the like CLI search for Markdown.
00:38:49.509 --> 00:38:56.469
I think Shopify is from Shopify or but anyway, yeah, that's cool.
00:38:56.630 --> 00:39:00.789
I hadn't thought about using Obsidian CLI.
00:39:00.869 --> 00:39:13.269
I heard that they had come out with CLI, but I hadn't thought about using obsidian features in your markdown files, like the linking and stuff, so that it's not having to draw these connections.
00:39:13.509 --> 00:39:15.110
The AI isn't having to do that.
00:39:15.429 --> 00:39:18.789
You don't necessarily need to have obsidian.
00:39:19.190 --> 00:39:21.429
You can just tag files, right?
00:39:21.509 --> 00:39:37.590
Like it is
nice that obsidian offers you a structured way of searching and building dashboards and whatnot, where like I can build a dashboard and it knows to go and look at that dashboard when I give it the good morning command because it looks at all my to-dos from the day prior and whatever.
00:39:37.989 --> 00:39:43.670
You know, when I tell it to wrap up a session, it knows exactly where to put the session, how it should look, because there's a template.
00:39:43.909 --> 00:39:48.469
That stuff could also be just in the command itself, like here's how to structure it.
00:39:48.550 --> 00:39:54.469
But it is nice to have the obsidian way of doing it that's already been iterated on, right?
00:39:54.550 --> 00:40:01.989
Like obsidian's already solved some of these problems, so it's nice to use it that way and have some structure for the AI.
00:40:02.550 --> 00:40:04.469
Whether or not it's the best way, I don't know.
00:40:04.550 --> 00:40:07.590
It just works for me right now, and I'm still tinkering with it.
00:40:07.670 --> 00:40:19.269
And every, almost every day I tweak something about the setup, or every week, you know, when I run the command, my weekly wrap-up command, I go, oh, you know what'd be better, or you know what I wish it had done?
00:40:19.349 --> 00:40:22.630
Or, you know, there's still a lot of manual, and it's still like coding, right?
00:40:22.710 --> 00:40:28.789
Like we still we build the simplest thing and then we iterate on it, we add more to it, and it'll evolve over time.
00:40:29.029 --> 00:40:46.949
And I'm sure someone will solve it in a way that either gets absorbed into how Claude handles its internal memory at the model level, or and maybe it is more of like the open claw way of doing things, but yeah, we'll see.
00:40:47.110 --> 00:40:53.110
It's interesting, it's an interesting problem to solve because it yeah, the models have amnesia.
00:40:53.190 --> 00:40:59.190
They don't know nothing about what's going on other than what we load into it, but they have a small context window.
00:40:59.269 --> 00:41:02.389
You can't load everything, you can't just be like, here's my app.
00:41:03.190 --> 00:41:11.590
So a little bit of job security is nice right now because like I know our app better than the AI does, but I don't know for how much longer.
00:41:11.909 --> 00:41:12.869
We'll see.
00:41:13.829 --> 00:41:20.789
Maybe it's worth you looking into too, is like, how can Obsidian solve some of these issues that I'm having?
00:41:21.029 --> 00:41:28.789
And the cool thing is you can just ask the AI, hey, I'm having this problem with your memory, considering a tool like Obsidian.
00:41:28.869 --> 00:41:29.429
What do you think?
00:41:29.509 --> 00:41:32.789
And it might give you some interesting suggestions.
00:41:33.429 --> 00:41:34.949
There's some resources online.
00:41:35.349 --> 00:41:36.710
Help unblog you a little bit?
00:41:36.789 --> 00:41:39.509
Or yeah, no, that gives me some things to think about.
00:41:39.829 -->
00:41:43.269
As much as the memory problem is interesting, and I'm sure someone's gonna solve it.
00:41:43.429 --> 00:41:55.909
I'm wondering how long it's gonna take to get to the point where token efficiency is so valued that that's what we put on our resume.
00:41:56.309 --> 00:42:15.190
How token efficient we are, how good we are at getting good results by using less tokens and like what tools we have built to say, oh, I built an agent harness that does X, Y, or Z under the hood before it prompts the LLM and it saves 20% of your tokens or whatever and reduces costs.
00:42:15.349 --> 00:42:28.789
Like, I know we have a pretty big budget for it at work because we're still in the exploration mode and we know we need to, but there's gotta be a tipping point where people go, okay, I'm not willing to spend this much money on this thing anymore.
00:42:29.029 --> 00:42:29.429
Right.
00:42:29.670 --> 00:42:30.789
Let's get efficient.
00:42:31.029 --> 00:42:39.829
You put on your resume, you know, migrated this many users to this new system and like shut down the legacy system or something like that.
00:42:39.989 --> 00:42:48.150
But in the new age, you have that line on your resume, but it says using only 150,000 tokens or something like that.
00:42:48.469 --> 00:42:52.630
Yeah, you go to join a new uh new org and they're like, let's see your clawed code stats.
00:42:52.710 --> 00:42:57.909
Yeah, how much do you how much money are you gonna cost us in addition to your salary?
00:42:58.150 --> 00:42:58.630
I don't know.
00:42:58.789 --> 00:42:59.750
Maybe that won't happen.
00:42:59.829 --> 00:43:09.909
Maybe the models will continue to get more efficient and cheaper and it won't be a problem, but maybe because we're having a huge shortage in RAM and GPUs and all the stuff that it uses.
00:43:10.150 --> 00:43:12.710
So that stuff's gonna start costing a premium.
00:43:12.869 --> 00:43:14.070
Maybe it is gonna happen.
00:43:14.230 --> 00:43:20.230
I've already started playing with the idea of like, okay, which model's better at planning, which model's better at building?
00:43:20.389 --> 00:43:32.309
Let's try this mode where I use like clawed opus in plan mode, and then I use open AI codecs in build mode and start looking at the differences and stuff.
00:43:32.389 --> 00:43:38.789
And then I I use open code, where most of my team is using clawed code.
00:43:38.869 --> 00:43:43.429
There's a few of us using open code, and open code's really cool because it's really easy to switch models.
00:43:43.590 --> 00:43:48.389
So I've gotten to play with, you know what, this task is like not a big ask.
00:43:48.469 --> 00:43:52.550
I'll give it to a dumber model, like a not as expensive model.
00:43:52.869 --> 00:43:59.029
Because I just don't feel like doing this boilerplate BS, but I don't think it needs the deep reasoning of Opus or Codec.
00:43:59.349 --> 00:44:15.110
So that doesn't matter right now because we don't have any restrictions, but I'm trying to get the muscle memory so that when we do have restrictions, and if we do have restrictions, that the muscle memory is already there to like certain tasks, certain models.
00:44:15.349 --> 00:44:21.509
Don't sort of like you don't give a senior engineer a junior level task because it's not cost effective.
00:44:21.750 --> 00:44:29.269
I don't know if that's going to be a thing in the future, but I have a sneaking suspicion it will, so I'm already trying to plan around that.
00:44:29.590 --> 00:44:35.750
Yeah, or just using the right tool for the job, like, or the right programming language for the right application.
00:44:35.829 --> 00:44:38.469
Like it's gonna be important, I think.
00:44:38.789 --> 00:45:07.190
There's another tool called Counselors that Aaron Francis made, and it basically is like giving the same prompt or problem to multiple models at once, and then one model will kind of summarize what they all said and kind of bring it all together and see if there is one implementation that is best fit from all of these different uh perspectives.
00:45:07.750 --> 00:45:08.070
Interesting.
00:45:08.309 --> 00:45:09.269
I thought that was kind of cool.
00:45:09.590 --> 00:45:11.590
Probably can get expensive to do.
00:45:11.989 --> 00:45:12.630
Oh yeah.
00:45:12.949 --> 00:45:13.590
Yeah.
00:45:14.949 --> 00:45:25.750
But yeah, interesting to like get the different perspectives and then maybe you just have one implement it based off of the best kind of case that was built from all of them.
00:45:25.909 --> 00:45:31.190
But I think efficiency will be will be important right now.
00:45:31.989 --> 00:45:36.070
People are kind of throwing it to the wind because you just have to experiment.
00:45:36.230 --> 00:45:37.590
There's just so much happening.
00:45:38.550 --> 00:45:39.989
How do you know if you don't experiment?
00:45:40.230 --> 00:45:40.550
Yep.
00:45:40.789 --> 00:45:41.909
You have to be free.
00:45:42.309 --> 00:45:53.670
So the last question, my favorite, is what is something cool, new, or interesting that you've recently learned, discovered, built, whatever, vibe coded, doesn't matter, that you want to share.
00:45:53.909 --> 00:45:56.070
Doesn't have to be coding related, it absolutely can be.
00:45:56.389 --> 00:45:59.029
I will plug Blast Off Rails here.
00:45:59.269 --> 00:46:04.550
It is new, so this will be the first time this conference has happened, and I hope that.
00:46:05.029 --> 00:46:06.710
It will be cool and interesting.
00:46:06.869 --> 00:46:10.550
I'm trying my very hardest to make it that.
00:46:11.110 --> 00:46:15.509
But yeah, it's happening this summer, June 11th and 12th.
00:46:15.829 --> 00:46:23.909
And it is a place for people to gather and kind of get energy.
00:46:24.230 --> 00:46:49.269
That's the reason that I have gone to and continue to go to conferences is there is for me, there isn't really a substitute for the energy that you get from being in a room with a bunch of people that are interested in
the same things as you and being kind of forced to sit through these talks.
00:46:49.429 --> 00:46:56.070
And I don't mean that in a negative way, like, but for me, I'll see these interesting talks, like YouTube videos.
00:46:56.230 --> 00:47:03.269
There's recordings of talks, there's people that put stuff on YouTube, there's interesting blog posts that I always like bookmark.
00:47:03.349 --> 00:47:04.630
I'm like, oh, that sounds really cool.
00:47:04.710 --> 00:47:05.750
I'm gonna listen to that later.
00:47:05.829 --> 00:47:06.869
I'm gonna watch that later.
00:47:07.029 --> 00:47:08.230
I'm gonna read that later.
00:47:08.389 --> 00:47:09.829
And I don't get around to it.
00:47:09.989 --> 00:47:23.509
But at a conference, you paid money to be in this room, and people are going to give you the blog posts, give you the YouTube video live, and you set this time aside to do that.
00:47:23.989 --> 00:47:27.269
And that's really special to me.
00:47:27.829 --> 00:47:35.829
So there's also a ton of other conferences happening that I'm going to them and I'll just plug them as well.
00:47:35.989 --> 00:47:46.869
There's RBQ in Austin in March, I believe into March, and then there's uh Blue Ridge Ruby happening in North Carolina.
00:47:47.110 --> 00:47:48.550
Yeah, Asheville, North Carolina.
00:47:48.789 --> 00:47:50.150
That's Jeremy Smith's baby.
00:47:50.230 --> 00:47:51.429
That's I've been to that one a few times.
00:47:51.590 --> 00:47:52.710
That's a great commentary.
00:47:52.949 --> 00:47:55.029
So that one's kind of still newish.
00:47:55.509 --> 00:47:55.670
Yeah.
00:47:55.989 --> 00:48:00.309
They did it and then took a year off, and then they're doing it again.
00:48:00.469 --> 00:48:02.869
So that one's returning.
00:48:03.429 --> 00:48:08.469
But then there's Blast Off Rails in June, June 11th and 12th.
00:48:08.630 --> 00:48:13.029
And then there's RubyConf in July.
00:48:13.590 --> 00:48:16.630
So I'm planning right now on going to all of those.
00:48:16.710 --> 00:48:19.989
So it's going to be a busy year, but I'm super excited.
00:48:20.230 --> 00:48:22.789
Don't forget there's Rocky Mountain Ruby in October.
00:48:22.869 --> 00:48:23.269
Yeah, yeah, yeah.
00:48:23.590 --> 00:48:26.150
I don't think they've announced the dates yet, but that's been going strong.
00:48:26.230 --> 00:48:28.150
And that's a I love that conference.
00:48:28.309 --> 00:48:29.269
I love the conference.
00:48:29.429 --> 00:48:33.269
Spike and Becky do such a great job putting it together.
00:48:33.349 --> 00:48:35.909
And I love Boulder, the city that it's in.
00:48:36.230 --> 00:48:41.590
I have pitched to my wife moving there on more than one occasion because I just love it out there.
00:48:41.829 --> 00:48:48.309
I love seeing the regionals come back, but also I'm like, damn, there's so many conferences I want to go to.
00:48:48.389 --> 00:48:50.949
I don't have the time to go to all of these.
00:48:51.029 --> 00:48:52.949
It's like trying to structure
my calendar.
00:48:53.110 --> 00:48:56.389
My we get some time to go to conferences, but not a ton.
00:48:56.469 --> 00:48:59.110
So I'm like, oh, I'm going to have to use PTO for some of this.
00:48:59.269 --> 00:49:01.590
And which places does my wife want to go to?
00:49:01.670 --> 00:49:07.269
Because then I can roll it into a vacation where she won't want to murder me for using all my vacation time going to conferences.
00:49:07.509 --> 00:49:08.389
So yeah.
00:49:08.630 --> 00:49:16.710
Actually, the one interesting thing that stands out about Blast off over some of the others is like, it's Blue Ridge Ruby, it's Rocky Mountain Ruby.
00:49:17.190 --> 00:49:20.309
Yours is Blast Off Rails, not Blast Off Ruby.
00:49:20.389 --> 00:49:24.869
So you're focusing more on the Rails aspect than just the general Ruby.
00:49:25.110 --> 00:49:31.110
Was that an intentional decision because everyone else was Ruby and you wanted to be different?
00:49:31.269 --> 00:49:38.389
Or was it just, well, I use Rails, or you wanted to keep the topic on Rails and be less about the Ruby language?
00:49:38.469 --> 00:49:41.829
Like, what was the motivator to making it blast off Rails?
00:49:42.309 --> 00:49:49.509
It was partly to sort of differentiate it from the more general Ruby conferences.
00:49:49.670 --> 00:50:03.190
Like one of the I think it was like a random piece of information from some book I read that was like actually making the thing more niche makes it more interesting to people.
00:50:03.349 --> 00:50:12.309
And you're more likely to get people to whatever it is, buy your product or come to your conference or use your tool or whatever.
00:50:12.469 --> 00:50:24.789
If it's more niche, because you can actually focus on satisfying people more because you are doing a more specific thing.
00:50:25.029 --> 00:50:26.070
Yeah, yeah, it makes sense.
00:50:26.389 --> 00:50:32.230
For me, I am more interested in the Rails stuff.
00:50:32.550 --> 00:50:38.150
I haven't written a lot of other software, to be honest.
00:50:38.389 --> 00:50:41.509
So I am mostly Rails apps.
00:50:41.989 --> 00:50:45.829
So that's like always been what I've kind of gravitated towards at conferences.
00:50:45.989 --> 00:50:47.110
So I was like, you know what?
00:50:47.190 --> 00:50:49.429
Let's make this conference more specific.
00:50:49.989 --> 00:51:02.309
And hopefully that will make it more interesting because you can expect, like, oh, I'm a Rails developer, I make Rails apps, I'm gonna go to this conference and it's single track.
00:51:02.389 --> 00:51:04.949
So if you're not interested in a talk, then you're out of luck.
00:51:05.110 --> 00:51:13.110
But yeah, if you're interested in Rails and you come to this conference, you're gonna get Rails content and stuff that's applicable to you.
00:51:13.349 --> 00:51:18.550
So yeah, ended up going with blast off Rails instead of blast off Ruby.
00:51:18.789 --> 00:51:19.190
Okay, cool.
00:51:19.269 --> 00:51:25.750
And Albuquerque,
New Mexico is definitely somewhere I haven't been for a conference before.
00:51:26.150 --> 00:51:28.710
Is there a big tech scene in Albuquerque?
00:51:28.789 --> 00:51:30.150
Is it just that's my backyard?
00:51:30.230 --> 00:51:30.789
So screw it.
00:51:30.869 --> 00:51:31.429
Everyone come here.
00:51:31.509 --> 00:51:35.269
It's a pretty cool place, and you're about to find out, or what's Albuquerque?
00:51:35.509 --> 00:51:39.429
I think there's a couple advantages to having a conference in Albuquerque.
00:51:39.670 --> 00:51:43.110
One is it's kind of centrally located.
00:51:43.269 --> 00:51:54.150
It's still in this like southwest of uh the US, but for most people, there's at least only one layover.
00:51:54.389 --> 00:52:00.230
A lot of times there's a lot of direct flights here from from most major airports.
00:52:00.550 --> 00:52:05.349
And our airport is also really small, so it's enjoyable.
00:52:05.670 --> 00:52:07.989
So you have the best of uh both worlds.
00:52:08.070 --> 00:52:17.590
Like you have a lot of direct flights, but there's only like one or two a day from all these cities, and so the airport's still pretty small, and it's not a nightmare to find your way around and stuff like that.
00:52:17.670 --> 00:52:20.550
There's one terminal, like you're not like taking a train around.
00:52:20.949 --> 00:52:24.550
You just described my least favorite part of some of these conferences.
00:52:24.949 --> 00:52:25.509
Yes.
00:52:26.469 --> 00:52:43.509
But Albuquerque is a cheap in terms of like cost of living, and it's cheaper to put on a conference here, and it's also your hotel is not gonna be$300,$400 a night to be near the conference.
00:52:43.750 --> 00:52:55.110
There's like$175 a night hotels that are within walking distance of this venue, so which is the the Albuquerque Museum, which I think is gonna be really awesome.
00:52:55.429 --> 00:53:02.710
Everybody that comes to the conference also just has free access to the museum, so you can learn about the place that you're coming to.
00:53:02.869 --> 00:53:05.989
So, yeah, there's a lot of uh cool stuff here.
00:53:06.070 --> 00:53:21.750
We don't have like uh big tech companies here, but I mean there are like there's Facebook data centers and stuff around, but I think it's just a nice place to visit and nice weather in June.
00:53:22.230 --> 00:53:32.309
It's just a nice place to have a conference and have it be an overall, generally good experience for every kind of person.
00:53:32.469 --> 00:53:36.550
So I'm really excited for people that haven't been here to come here and experience it.
00:53:36.789 --> 00:53:37.909
Yeah, very cool, very cool.
00:53:37.989 --> 00:53:46.309
I like how accessible it'll be from a cost standpoint, too, especially with not every software company out there is sending people to conferences right now.
00:53:46.389 --> 00:53:48.070
So a junior might have to pay their own way.
00:53:48.230 --> 00:53:54.869
And if this is going to be the most cost-effective conference they can make in the year, that's a pretty big selling point.
00:53:55.349 --> 00:53:57.750
It can get expensive going to a lot of conferences.
00:53:57.909 --> 00:54:11.670
So we have like a budget for conferences at work, and it's really easy to blow through that really quickly because you're a couple hundred dollars at least for the flight.
00:54:11.909 --> 00:54:30.710
If you're gonna stay three nights for a two-day conference, at the very least, you're talking about over a thousand dollars for a hotel or close around there, even if you're staying at like a$300,$250 a night hotel that nowadays is the cheap ones, especially in major cities.
00:54:30.949 --> 00:54:35.670
You're over a thousand dollars for every conference that you go to if you're on a shoestring.
00:54:36.150 --> 00:54:44.070
And I think you could do this conference, depending on your flight, you could do this conference for less than a thousand dollars.
00:54:44.230 --> 00:55:06.389
Because early bird tickets, which there's 30 of them, there will just be that until they're gone, but they're only under$75,$175, and you get two or three nights, or three nights, let's say, at$175 at the best western down the street, which is a nice best western.
00:55:06.469 --> 00:55:09.750
I actually worked there before I became a programmer.
00:55:10.230 --> 00:55:15.909
You have one forty dollar Uber from the airport, another$40 to get back.
00:55:16.070 --> 00:55:18.389
Everything else around the conference is walkable.
00:55:18.869 --> 00:55:22.469
I think it could be a very uh cost-effective conference.
00:55:22.789 --> 00:55:27.750
And your CFP is closed, so you're gonna have the announcement for who's speaking soon.
00:55:27.909 --> 00:55:28.550
Do you have a date?
00:55:28.789 --> 00:55:29.750
That'll be coming soon.
00:55:29.909 --> 00:55:30.630
I don't have a date.
00:55:30.789 --> 00:55:33.190
Trying to confirm people right now.
00:55:33.670 --> 00:55:44.550
It'll be probably early March when I make that announcement, just so I can get everybody confirmed and get that all up on the website and everything.
00:55:44.630 --> 00:55:46.550
So very excited about that, though.
00:55:46.869 --> 00:55:48.230
Sounds like it's gonna be a great one.
00:55:48.389 --> 00:55:55.349
Good excuse to go to Albuquerque, New Mexico for the first time and blastoffrouse.com.
00:55:55.909 --> 00:56:01.829
Sounds like early bird tickets are very affordable, so don't sleep on those.
00:56:02.070 --> 00:56:06.869
Where can people find you on the web other than blastoffruby.com?
00:56:07.269 --> 00:56:11.029
Because of the conference, trying to get the word out there, I'm on everything.
00:56:11.190 --> 00:56:15.670
I'm on uh blue sky, I'm on X, I'm on LinkedIn.
00:56:15.989 --> 00:56:22.630
I think if you just search my name, you can find me most of those places.
00:56:23.269 --> 00:56:32.949
And uh you might have to look at the picture to try to match my face because there aren't many Travis doctors in the world, but there's at least like two others.
00:56:34.230 --> 00:56:38.630
Yeah, and your doctor with it's a D-O-C-K-T-E-R.
00:56:39.110 --> 00:56:44.630
Yeah, which probably the best way to find me is to look at the Blast Off Rails social account.
00:56:44.869 --> 00:56:49.269
And I think usually I'm like reposting it or something, you can find me pretty easily.
00:56:49.429 --> 00:56:49.909
Yeah, cool.
00:56:50.150 --> 00:56:54.230
We can also put links in the show notes to make it a little easier for people to find you.
00:56:54.389 --> 00:56:55.110
So awesome.
00:56:55.190 --> 00:56:56.550
Well, thanks for coming on the show, man.
00:56:56.630 --> 00:56:57.349
I really appreciate it.
00:56:57.590 --> 00:57:02.550
Appreciate your time and looking forward to seeing how uh a Blast Off Ruby comes together.
00:57:02.869 --> 00:57:05.750
Yeah, thank you for the time and all the good conversation.
00:57:05.909 --> 00:57:08.550
All right, listeners, we'll see you in the next one.